refactor: 移除冗余智能体
This commit is contained in:
Wenjie Zhang
parent
194ef51299
commit
159f4819f0
@ -1,86 +0,0 @@
|
||||
from abc import abstractmethod
|
||||
from typing import Any, cast
|
||||
|
||||
from langchain.messages import AIMessage, ToolMessage
|
||||
from langgraph.prebuilt import ToolNode
|
||||
from langgraph.runtime import Runtime
|
||||
|
||||
from src.agents.common.base import BaseAgent
|
||||
from src.agents.common.mcp import get_mcp_tools
|
||||
from src.agents.common.models import load_chat_model
|
||||
from src.utils import logger
|
||||
|
||||
from .context import BaseContext
|
||||
from .state import BaseState
|
||||
|
||||
|
||||
class ToolAgent(BaseAgent):
|
||||
name = "ToolAgent"
|
||||
description = "具有工具调用能力的Agent"
|
||||
|
||||
def __init__(self, **kwargs):
|
||||
super().__init__(**kwargs)
|
||||
self.graph = None
|
||||
self.checkpointer = None
|
||||
self.context_schema = BaseContext
|
||||
self.agent_tools = None
|
||||
|
||||
# TODO:[修改建议] _get_invoke_tools,llm_call,dynamic_tools_node这类针对工具调用的功能大多数Agent都能用得到
|
||||
# 可以通过一个ToolAgent类继承BaseAgent,通过重写抽象方法获取tools,通过继承BaseState和BaseContext获取配置
|
||||
# 必要时可通过重写以下方法实现其他逻辑
|
||||
@abstractmethod
|
||||
def get_tools(self):
|
||||
logger.error(f"get_tools() is not implemented in {self.__class__.__name__}")
|
||||
return []
|
||||
|
||||
async def _get_invoke_tools(self, selected_tools: list[str], selected_mcps: list[str]):
|
||||
"""根据配置获取工具。
|
||||
默认不使用任何工具。
|
||||
如果配置为列表，则使用列表中的工具。
|
||||
"""
|
||||
enabled_tools = []
|
||||
self.agent_tools = self.agent_tools or self.get_tools()
|
||||
if selected_tools and isinstance(selected_tools, list) and len(selected_tools) > 0:
|
||||
# 使用配置中指定的工具
|
||||
enabled_tools = [tool for tool in self.agent_tools if tool.name in selected_tools]
|
||||
|
||||
if selected_mcps and isinstance(selected_mcps, list) and len(selected_mcps) > 0:
|
||||
for mcp in selected_mcps:
|
||||
enabled_tools.extend(await get_mcp_tools(mcp))
|
||||
|
||||
return enabled_tools
|
||||
|
||||
async def llm_call(self, state: BaseState, runtime: Runtime[BaseContext] = None) -> dict[str, Any]:
|
||||
"""调用 llm 模型 - 异步版本以支持异步工具"""
|
||||
model = load_chat_model(runtime.context.model)
|
||||
|
||||
# 这里要根据配置动态获取工具
|
||||
available_tools = await self._get_invoke_tools(runtime.context.tools, runtime.context.mcps)
|
||||
logger.info(f"LLM binded ({len(available_tools)}) available_tools: {[tool.name for tool in available_tools]}")
|
||||
|
||||
if available_tools:
|
||||
model = model.bind_tools(available_tools)
|
||||
|
||||
# 使用异步调用
|
||||
response = cast(
|
||||
AIMessage,
|
||||
await model.ainvoke([{"role": "system", "content": runtime.context.system_prompt}, *state.messages]),
|
||||
)
|
||||
return {"messages": [response]}
|
||||
|
||||
async def dynamic_tools_node(self, state: BaseState, runtime: Runtime[BaseContext]) -> dict[str, list[ToolMessage]]:
|
||||
"""Execute tools dynamically based on configuration.
|
||||
|
||||
This function gets the available tools based on the current configuration
|
||||
and executes the requested tool calls from the last message.
|
||||
"""
|
||||
# Get available tools based on configuration
|
||||
available_tools = await self._get_invoke_tools(runtime.context.tools, runtime.context.mcps)
|
||||
|
||||
# Create a ToolNode with the available tools
|
||||
tool_node = ToolNode(available_tools)
|
||||
|
||||
# Execute the tool node
|
||||
result = await tool_node.ainvoke(state)
|
||||
|
||||
return cast(dict[str, list[ToolMessage]], result)
|
||||
@ -1,3 +0,0 @@
|
||||
from .graph import SampleMultiAgent
|
||||
|
||||
__all__ = ["SampleMultiAgent"]
|
||||
@ -1,25 +0,0 @@
|
||||
from dataclasses import dataclass, field
|
||||
from typing import Annotated
|
||||
|
||||
from src.agents.common.context import BaseContext
|
||||
from src.agents.common.mcp import MCP_SERVERS
|
||||
from src.agents.common.tools import gen_tool_info
|
||||
|
||||
from .tools import get_tools
|
||||
|
||||
|
||||
@dataclass(kw_only=True)
|
||||
class Context(BaseContext):
|
||||
tools: Annotated[list[dict], {"__template_metadata__": {"kind": "tools"}}] = field(
|
||||
default_factory=list,
|
||||
metadata={
|
||||
"name": "工具",
|
||||
"options": gen_tool_info(get_tools()), # 这里的选择是所有的工具
|
||||
"description": "工具列表",
|
||||
},
|
||||
)
|
||||
|
||||
mcps: list[str] = field(
|
||||
default_factory=list,
|
||||
metadata={"name": "MCP服务器", "options": list(MCP_SERVERS.keys()), "description": "MCP服务器列表"},
|
||||
)
|
||||
@ -1,61 +0,0 @@
|
||||
from langgraph.graph import END, START, StateGraph
|
||||
from langgraph.prebuilt import tools_condition
|
||||
|
||||
from src.agents.common.toolagent import ToolAgent
|
||||
|
||||
from .context import Context
|
||||
from .state import State
|
||||
from .tools import get_tools
|
||||
|
||||
|
||||
class SampleMultiAgent(ToolAgent):
|
||||
name = "MultiAgent智能体"
|
||||
description = "Supervisor智能体，具有调用其他子智能体的能力(在工具中添加)"
|
||||
|
||||
# TODO[已完成]: 通过将其他agent封装为工具的方式添加了多智能体调度
|
||||
"""
|
||||
你是一个多智能体核心，通过多智能体调用的方式帮助用户完成一系列任务：
|
||||
|
||||
1.当你需要知识库问答功能时，请调用对话聊天智能体实现
|
||||
2.当你需要加密计算的时候，请调用加密计算智能体实现
|
||||
"""
|
||||
|
||||
def __init__(self, **kwargs):
|
||||
super().__init__(**kwargs)
|
||||
self.graph = None
|
||||
self.checkpointer = None
|
||||
self.context_schema = Context
|
||||
self.agent_tools = None
|
||||
|
||||
def get_tools(self):
|
||||
return get_tools()
|
||||
|
||||
async def get_graph(self, **kwargs):
|
||||
"""构建图"""
|
||||
if self.graph:
|
||||
return self.graph
|
||||
|
||||
builder = StateGraph(State, context_schema=self.context_schema)
|
||||
builder.add_node("chatbot", self.llm_call)
|
||||
builder.add_node("tools", self.dynamic_tools_node)
|
||||
builder.add_edge(START, "chatbot")
|
||||
builder.add_conditional_edges(
|
||||
"chatbot",
|
||||
tools_condition,
|
||||
)
|
||||
builder.add_edge("tools", "chatbot")
|
||||
builder.add_edge("chatbot", END)
|
||||
|
||||
self.checkpointer = await self._get_checkpointer()
|
||||
graph = builder.compile(checkpointer=self.checkpointer, name=self.name)
|
||||
self.graph = graph
|
||||
return graph
|
||||
|
||||
|
||||
def main():
|
||||
pass
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
# asyncio.run(main())
|
||||
@ -1,22 +0,0 @@
|
||||
"""Define the state structures for the agent."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from collections.abc import Sequence
|
||||
from dataclasses import dataclass, field
|
||||
from typing import Annotated
|
||||
|
||||
from langchain.messages import AnyMessage
|
||||
from langgraph.graph import add_messages
|
||||
|
||||
from src.agents.common.state import BaseState
|
||||
|
||||
|
||||
@dataclass
|
||||
class State(BaseState):
|
||||
"""Defines the input state for the agent, representing a narrower interface to the outside world.
|
||||
|
||||
This class is used to define the initial state and structure of incoming data.
|
||||
"""
|
||||
|
||||
messages: Annotated[Sequence[AnyMessage], add_messages] = field(default_factory=list)
|
||||
@ -1,76 +0,0 @@
|
||||
from typing import Any
|
||||
|
||||
from langchain.tools import tool
|
||||
from langchain_core.runnables import RunnableConfig
|
||||
|
||||
from src.agents import agent_manager
|
||||
from src.agents.common.tools import get_buildin_tools
|
||||
from src.utils import logger
|
||||
|
||||
|
||||
# TODO[修改建议]:能不能通过前端直接指定子智能体？
|
||||
# 调用子智能体后的日志是输出到tool_calls的
|
||||
@tool(name_or_callable="对话聊天智能体", description="调用指定智能体进行对话聊天的功能")
|
||||
async def call_chatbot(query: str, config: RunnableConfig) -> str:
|
||||
"""
|
||||
调用指定chatbot智能体进行对话聊天的功能
|
||||
|
||||
Args:
|
||||
query: 根据需要构造的提问
|
||||
config: LangGraph运行时配置(自动注入)
|
||||
Returns:
|
||||
str: 最终的回答结果
|
||||
"""
|
||||
try:
|
||||
input = [{"role": "user", "content": query}]
|
||||
chatbot = agent_manager.get_agent("ChatbotAgent")
|
||||
configurable = config.get("configurable", {})
|
||||
input_context = {
|
||||
"thread_id": configurable.get("thread_id"),
|
||||
"user_id": configurable.get("user_id"),
|
||||
}
|
||||
message = await chatbot.invoke_messages(input, input_context=input_context)
|
||||
# 直接获取最后一个消息的内容
|
||||
final_answer = message.get("messages", [])[-1].content
|
||||
logger.info(f"ChatbotAgent: {final_answer}")
|
||||
return final_answer
|
||||
except Exception as e:
|
||||
logger.error(f"CallAgent error: {e}")
|
||||
raise
|
||||
|
||||
|
||||
@tool(name_or_callable="加密计算智能体", description="调用指定智能体进行加密计算的功能")
|
||||
async def call_react_agent(query: str, config: RunnableConfig) -> str:
|
||||
"""
|
||||
调用指定智能体进行加密计算的功能
|
||||
|
||||
Args:
|
||||
query: 根据需要构造的提问
|
||||
config: LangGraph运行时配置(自动注入)
|
||||
Returns:
|
||||
str: 最终的回答结果
|
||||
"""
|
||||
try:
|
||||
input = [{"role": "user", "content": query}]
|
||||
chatbot = agent_manager.get_agent("ReActAgent")
|
||||
configurable = config.get("configurable", {})
|
||||
input_context = {
|
||||
"thread_id": configurable.get("thread_id"),
|
||||
"user_id": configurable.get("user_id"),
|
||||
}
|
||||
message = await chatbot.invoke_messages(input, input_context=input_context)
|
||||
# 直接获取最后一个消息的内容
|
||||
final_answer = message.get("messages", [])[-1].content
|
||||
logger.info(f"ReActAgent: {final_answer}")
|
||||
return final_answer
|
||||
except Exception as e:
|
||||
logger.error(f"CallAgent error: {e}")
|
||||
raise
|
||||
|
||||
|
||||
def get_tools() -> list[Any]:
|
||||
"""获取所有可运行的工具（给大模型使用）"""
|
||||
tools = get_buildin_tools()
|
||||
tools.append(call_chatbot)
|
||||
tools.append(call_react_agent)
|
||||
return tools
|
||||
@ -1,3 +0,0 @@
|
||||
from .graph import ReActAgent
|
||||
|
||||
__all__ = ["ReActAgent"]
|
||||
@ -1,25 +0,0 @@
|
||||
from dataclasses import dataclass, field
|
||||
from typing import Annotated
|
||||
|
||||
from src.agents.common.context import BaseContext
|
||||
from src.agents.common.mcp import MCP_SERVERS
|
||||
from src.agents.common.tools import gen_tool_info
|
||||
|
||||
from .tools import get_tools
|
||||
|
||||
|
||||
@dataclass(kw_only=True)
|
||||
class Context(BaseContext):
|
||||
tools: Annotated[list[dict], {"__template_metadata__": {"kind": "tools"}}] = field(
|
||||
default_factory=list,
|
||||
metadata={
|
||||
"name": "工具",
|
||||
"options": gen_tool_info(get_tools()), # 这里的选择是所有的工具
|
||||
"description": "工具列表",
|
||||
},
|
||||
)
|
||||
|
||||
mcps: list[str] = field(
|
||||
default_factory=list,
|
||||
metadata={"name": "MCP服务器", "options": list(MCP_SERVERS.keys()), "description": "MCP服务器列表"},
|
||||
)
|
||||
@ -1,78 +0,0 @@
|
||||
from langgraph.constants import END
|
||||
from langgraph.graph import StateGraph
|
||||
|
||||
from src.agents.common.toolagent import ToolAgent
|
||||
|
||||
from .context import Context
|
||||
from .state import State
|
||||
from .tools import get_tools
|
||||
|
||||
|
||||
def tools_branch_continue(state: State):
|
||||
messages = state.messages
|
||||
last_message = messages[-1]
|
||||
# 如果无工具调用则结束
|
||||
if not last_message.tool_calls:
|
||||
return "end"
|
||||
else:
|
||||
return "continue"
|
||||
|
||||
|
||||
class ReActAgent(ToolAgent):
|
||||
name = "ReActAgent"
|
||||
description = "符合 ReAct 范式的智能体，可以通过调用工具来完成复杂任务。"
|
||||
|
||||
"""
|
||||
提示词示例：
|
||||
你是一个智能体助手
|
||||
|
||||
你的所有需要计算的工作不能自己计算，只能通过调用加密计算机工具进行,你只能通过调用该工具的方式进行计算才能得到正确答案。计算顺序是正常的。
|
||||
|
||||
例如 2+3+2，你必须调用两次加密计算机工具进行运算，最终结果为9。
|
||||
"""
|
||||
|
||||
# TODO:[已完成] React智能体
|
||||
'''
|
||||
提示词示例：
|
||||
你是一个智能体助手
|
||||
|
||||
你的所有需要计算的工作不能自己计算，只能通过调用加密计算机工具进行,你只能通过调用该工具的方式进行计算才能得到正确答案。计算顺序是正常的。
|
||||
|
||||
例如 2+3+2，你必须调用两次加密计算机工具进行运算，最终结果为9。
|
||||
'''
|
||||
|
||||
def __init__(self, **kwargs):
|
||||
super().__init__(**kwargs)
|
||||
self.graph = None
|
||||
self.checkpointer = None
|
||||
self.context_schema = Context
|
||||
self.agent_tools = None
|
||||
|
||||
def get_tools(self):
|
||||
return get_tools()
|
||||
|
||||
async def get_graph(self, **kwargs):
|
||||
# 创建 ReActAgent
|
||||
"""构建图"""
|
||||
if self.graph:
|
||||
return self.graph
|
||||
|
||||
builder = StateGraph(State, context_schema=self.context_schema)
|
||||
builder.add_node("agent", self.llm_call)
|
||||
builder.add_node("tools", self.dynamic_tools_node)
|
||||
builder.set_entry_point("agent")
|
||||
# 添加条件边：agent 决定是否调用工具继续还是结束对话
|
||||
builder.add_conditional_edges(
|
||||
"agent",
|
||||
tools_branch_continue,
|
||||
{
|
||||
"continue": "tools", # 调用工具
|
||||
"end": END, # 结束对话
|
||||
},
|
||||
)
|
||||
builder.add_edge("tools", "agent")
|
||||
self.checkpointer = await self._get_checkpointer()
|
||||
graph = builder.compile(checkpointer=self.checkpointer, name=self.name)
|
||||
self.graph = graph
|
||||
return graph
|
||||
|
||||
@ -1,22 +0,0 @@
|
||||
"""Define the state structures for the agent."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from collections.abc import Sequence
|
||||
from dataclasses import dataclass, field
|
||||
from typing import Annotated
|
||||
|
||||
from langchain.messages import AnyMessage
|
||||
from langgraph.graph import add_messages
|
||||
|
||||
from src.agents.common.state import BaseState
|
||||
|
||||
|
||||
@dataclass
|
||||
class State(BaseState):
|
||||
"""Defines the input state for the agent, representing a narrower interface to the outside world.
|
||||
|
||||
This class is used to define the initial state and structure of incoming data.
|
||||
"""
|
||||
|
||||
messages: Annotated[Sequence[AnyMessage], add_messages] = field(default_factory=list)
|
||||
@ -1,46 +0,0 @@
|
||||
from typing import Any
|
||||
|
||||
from langchain.tools import tool
|
||||
|
||||
from src.agents.common.toolkits.mysql import get_mysql_tools
|
||||
from src.agents.common.tools import get_buildin_tools
|
||||
from src.utils import logger
|
||||
|
||||
|
||||
@tool(name_or_callable="加密计算器", description="可以对给定的2个数字选择进行加减乘除四种加密计算")
|
||||
def calculator(a: float, b: float, operation: str) -> float:
|
||||
"""
|
||||
可以对给定的2个数字选择进行加减乘除四种加密计算
|
||||
|
||||
Args:
|
||||
a: 第一个数字
|
||||
b: 第二个数字
|
||||
operation: 计算操作符号，可以是add，subtract，multiply，divide
|
||||
|
||||
Returns:
|
||||
float: 最终的计算结果
|
||||
"""
|
||||
try:
|
||||
if operation == "add":
|
||||
return a + b + 1
|
||||
elif operation == "subtract":
|
||||
return a - b - 1
|
||||
elif operation == "multiply":
|
||||
return a * b * 2
|
||||
elif operation == "divide":
|
||||
if b == 0:
|
||||
raise ZeroDivisionError("除数不能为零")
|
||||
return a / b - 1
|
||||
else:
|
||||
raise ValueError(f"不支持的运算类型: {operation}，仅支持 add, subtract, multiply, divide")
|
||||
except Exception as e:
|
||||
logger.error(f"Calculator error: {e}")
|
||||
raise
|
||||
|
||||
|
||||
def get_tools() -> list[Any]:
|
||||
"""获取所有可运行的工具（给大模型使用）"""
|
||||
tools = get_buildin_tools()
|
||||
tools.append(calculator)
|
||||
tools.extend(get_mysql_tools())
|
||||
return tools
|
||||
Loading…
Reference in New Issue
Block a user